← Back to community benchmarks

gemma-4-26b-a4b-it

M5 (10c) · 24 GB · 4bit · 2026-05-17
Performance
16k
tokens
907.9
PP tok/s
33.9
TG tok/s
18046
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 832.2 42.6 14.2 GB view
4k 935.5 40.5 14.9 GB view
8k 952.2 37.9 15.0 GB view
16k 907.9 33.9 15.5 GB current
32k 756.2 27.0 16.4 GB view
64k 459.5 14.6 17.7 GB view